FedARKS: Federated Aggregation via Robust and Discriminative Knowledge Selection and Integration for Person Re-identification

TL;DR

FedARKS introduces a federated learning framework for person re-identification that enhances domain generalization by selectively aggregating robust, discriminative knowledge from clients, addressing limitations of global features and uniform averaging.

Contribution

The paper proposes FedARKS, a novel federated learning method with knowledge selection and integration mechanisms to improve person re-identification across unseen domains.

Findings

Improved generalization to unseen domains in person re-identification.

Effective knowledge selection enhances model robustness and discriminative ability.

Outperforms existing federated learning approaches in ReID tasks.

Abstract

The application of federated domain generalization in person re-identification (FedDG-ReID) aims to enhance the model's generalization ability in unseen domains while protecting client data privacy. However, existing mainstream methods typically rely on global feature representations and simple averaging operations for model aggregation, leading to two limitations in domain generalization: (1) Using only global features makes it difficult to capture subtle, domain-invariant local details (such as accessories or textures); (2) Uniform parameter averaging treats all clients as equivalent, ignoring their differences in robust feature extraction capabilities, thereby diluting the contributions of high quality clients. To address these issues, we propose a novel federated learning framework, Federated Aggregation via Robust and Discriminative Knowledge Selection and Integration (FedARKS), comprising two mechanisms: RK (Robust Knowledge) and KS (Knowledge Selection).